Presentation Outline What the project is What has been completed - - PowerPoint PPT Presentation

▶
presentation outline
SMART_READER_LITE
LIVE PREVIEW

Presentation Outline What the project is What has been completed - - PowerPoint PPT Presentation

Oct 07, 2023 18 likes •631 views

VBASR: The Vision System V ision B ased A utonomous S ecurity R obot Bradley University ECE Department Senior Capstone Project Sponsored by Northrup Grumman May 04, 2010 Student: Kevin Farney Advisor: Dr. Joel Schipper Presentation

slide-1
SLIDE 1
slide-2
SLIDE 2

VBASR: The Vision System Vision Based Autonomous Security Robot

Bradley University – ECE Department Senior Capstone Project

Sponsored by Northrup Grumman May 04, 2010

Student: Kevin Farney Advisor:

  • Dr. Joel Schipper
slide-3
SLIDE 3

Presentation Outline

 What the project is…  What has been completed…  Results…

2

slide-4
SLIDE 4

Project Summary

 What is VBASR?

 Autonomous, Mobile, Security Camera

 VBASR is a computer vision project  Primary Goals – Using Computer Vision

 Navigation

 Obstacle Avoidance

3

slide-5
SLIDE 5

Vision Algorithm

 System Block Diagram

4

slide-6
SLIDE 6

The Platform

 Hardware

 iRobot Create  Webcam

 Software

 OpenCV2.0

5

slide-7
SLIDE 7

Vision Algorithm – Idea #1

6

slide-8
SLIDE 8

Vision Algorithm – Idea #2

7

slide-9
SLIDE 9

Vision Algorithm – Idea #3

8

slide-10
SLIDE 10

Vision Algorithm – High Level

9

slide-11
SLIDE 11

Vision Algorithm – Detailed

Feature Extraction

10

slide-12
SLIDE 12

Feature Extraction

11

slide-13
SLIDE 13

Testing OpenCV - Filters

12

slide-14
SLIDE 14

Testing OpenCV - Filters

13

slide-15
SLIDE 15

Testing OpenCV - Filters

14

slide-16
SLIDE 16

Feature Extraction

15

slide-17
SLIDE 17

Testing OpenCV - Edge

16

slide-18
SLIDE 18

Why Filters?

 Noise Reduction

17

slide-19
SLIDE 19

Feature Extraction

18

slide-20
SLIDE 20

Testing OpenCV - Corners

19

slide-21
SLIDE 21

Feature Extraction

20

slide-22
SLIDE 22

Testing OpenCV – Flood Fill

21

slide-23
SLIDE 23

Vision Algorithm – Detailed

Lines Algorithm Feature Extraction

22

slide-24
SLIDE 24

Lines Algorithm

Feature Extraction

23

slide-25
SLIDE 25

Lines Algorithm

24

slide-26
SLIDE 26

Vision Algorithm – Detailed

Corners Algorithm

25

slide-27
SLIDE 27

Corners Algorithm

Feature Extraction

26

slide-28
SLIDE 28

Corners Algorithm

27

slide-29
SLIDE 29

Vision Algorithm – Detailed

Colors Algorithm

28

slide-30
SLIDE 30

Colors Algorithm

Feature Extraction

29

slide-31
SLIDE 31

Colors Algorithm

30

slide-32
SLIDE 32

Vision Algorithm – Detailed

31

slide-33
SLIDE 33

Vision Algorithm - Example One

32

slide-34
SLIDE 34

Vision Algorithm - Example One

33

slide-35
SLIDE 35

Vision Algorithm - Example One

34

slide-36
SLIDE 36

Vision Algorithm - Example One

35

slide-37
SLIDE 37

Vision Algorithm - Example One

36

slide-38
SLIDE 38

Vision Algorithm - Example Two

37

slide-39
SLIDE 39

Vision Algorithm - Example Two

38

slide-40
SLIDE 40

Vision Algorithm - Example Two

39

slide-41
SLIDE 41

Vision Algorithm - Example Two

40

slide-42
SLIDE 42

Vision Algorithm - Example Two

41

slide-43
SLIDE 43

Quantitative Results

42

slide-44
SLIDE 44

Qualitative Results

 Initial testing yields promising results!

 Two programs ran independently

 Vision system  iRobot controls

 Verified quantitative results  Exceeded expectations

43

slide-45
SLIDE 45

Questions?

 VBASR by Kevin Farney

44

slide-46
SLIDE 46

References

Sage, K., and S. Young. "Security Applications of Computer Vision." IEEE Transactions on Aerospace and Electronic Systems 14.4 (1999): 19-29. Aug. 2002.

DeSouza, G. N., and A. C. Kak. "Vision for Mobile Robot Navigation: A Survey." IEEE Transactions on Pattern Analysis and Machine Intelligence 24.2 (2002): 237-67. Aug. 2002.

Davies, E. R. Machine Vision: Theory, Algorithms, Practicalities. San Francisco: Morgan Kaufmann, 2005.

Forsyth, D., and J. Ponce. Computer Vision: a Modern Approach. Upper Saddle River, N.J.: Prentice Hall, 2003.

Shapiro, Linda G., and George C. Stockman. Computer Vision. Upper Saddle River, NJ: Prentice Hall, 2001.

45

slide-47
SLIDE 47

References

Scott, D., and F. Aghdasi. "Mobile Robot Navigation In Unstructured Environments Using Machine Vision." IEEE AFRICON 1 (1999): 123-26. Aug. 2002.

Argyros, A. A., and F. Bergholm. "Combining Central and Peripheral Vision for Reactive Robot Navigation." IEEE CSC Computer Vision and Pattern Recognition 2 (1999): 646-51. Aug. 2002.

Shimizu, S., T. Kato, Y. Ocmula, and R. Suematu. "Wide Angle Vision Sensor with Fovea-navigation of Mobile Robot Based on Cooperation between Central Vision and Peripheral Vision." IEEE/RSJ Intelligent Robots and Systems 2 (2001): 764-

  • 71. Aug. 2002.

Matsumoto, Y., K. Ikeda, M. Inaba, and H. Inoue. "Visual Navigation Using Omnidirectional View Sequence." IEEE/RSJ Intelligent Robots and Systems 1 (1999): 317-22. Aug. 2002.

Orghidan, R., J. Salvi, and E. M. Mouaddib. "Accuracy Estimation of a New Omnidirectional 3D Vision Sensor." IEEE/ICIP Image Processing 3 (2005): 365-

  • 68. Mar. 2006.

46

slide-48
SLIDE 48

References

Kosinski, R. J. "Literature Review on Reaction Time." Clemson University, Aug.

  • 2009. 10 Nov. 2009. <http://biae.clemson.edu/bpc/bp/Lab/110/reaction.htm>

Canny, J. "A Computational Approach to Edge Detection." IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-8.6 (1986): 679-98. Jan. 2009.

Shi, W., and J. Samarabandu. "CORRIDOR LINE DETECTION FOR VISION BASED INDOOR ROBOT NAVIGATION." IEEE CCECE (2006): 1988-991. Jan. 2007.

Marques, C., and P. Lima. "Multisensor Navigation for Nonholonomic Robots in Cluttered Environments." IEEE Transactions on Robotics and Automation 11.3 (2004): 70-82. Oct. 2004.

Ohya, I., A. Kosaka, and A. Kak. "Vision-Based Navigation by a Mobile Robot with Obstacle Avoidance Using Single-Camera Vision and Ultrasonic Sensing." IEEE Transactions on Robotics and Automation 14.6 (1998): 969-78. Aug. 2002.

47

slide-49
SLIDE 49

Quantitative Results

48

slide-50
SLIDE 50

Selecting Parameter Values

49

slide-51
SLIDE 51

Lines Algorithm - Problems

50

slide-52
SLIDE 52

Corners Algorithm - Problems

51

slide-53
SLIDE 53

Colors Algorithm - Problems

52

slide-54
SLIDE 54

Colors Algorithm - Solution

53

slide-55
SLIDE 55

Filters - Normal

 Normal Blur

 Normalized box filter – summation of pixels

  • ver a neighborhood

54

slide-56
SLIDE 56

Filters – Gaussian

 Gaussian Blur

 Convolution of source image with specified

gaussian kernel

= Matrix of ksize (parameter) x 1 with filter coefficients:

55

slide-57
SLIDE 57

Filters

 Median Blur

 Returns median of pixel neighborhood into

the destination image for each pixel

56

slide-58
SLIDE 58

Canny Edge Detection

 Implements Canny Algorithm

 First noise-reduction needed (filters)  Intensity Gradients

 8 points

 Non-Maximum Suppression  Hysteresis Thresholding

 High – discards noisy pixels  Low – connects the edges into lines (binary)

57

slide-59
SLIDE 59

Corner Detection

 Good Features To Track

 Calculates minimal eigenvalue per pixel

 Covariation Matrix of derivatives  Then eigenvalues represent corners

 Non-maxima suppression (3x3 pixels)  Rejection by quality level (parameter)

 qualityLevel•max(eigImage(x,y))

 Rejection by distance (parameter)

58

slide-60
SLIDE 60

Price Breakdown

 iRobot Create Premium Development Package

 $299

 Pioneer 3-DX

 upwards of $5000

 Microsoft Robotics Developers Studio R2

 free download

 Visual Studio 2008

 $500 and up  Visual C# editor – free download

 Small Netbook

 Looking for around $300

59

slide-61
SLIDE 61

Microsoft Robotics Developer Studio

 CCR (Concurrency and Coordination

Runtime)

 DSS (Decentralized Software Services)  VPL (Visual Programming Language)  VSE (Visual Simulation Environment)

60